02/02/2021

A One-Size-Fits-All Solution to Conservative Bandit Problems

Yihan Du, Siwei Wang, Longbo Huang

Keywords:

Abstract Paper Similar Papers

Abstract: In this paper, we study a family of conservative bandit problems (CBPs) with sample-path reward constraints, i.e., the learner's reward performance must be at least as well as a given baseline at any time. We propose a One-Size-Fits-All solution to CBPs and present its applications to three encompassed problems, i.e. conservative multi-armed bandits (CMAB), conservative linear bandits (CLB) and conservative contextual combinatorial bandits (CCCB). Different from previous works which consider high probability constraints on the expected reward, we focus on a sample-path constraint on the actually received reward, and achieve better theoretical guarantees (T-independent additive regrets instead of T-dependent) and empirical performance. Furthermore, we extend the results and consider a novel conservative mean-variance bandit problem (MV-CBP), which measures the learning performance with both the expected reward and variability. For this extended problem, we provide a novel algorithm with O(1/T) normalized additive regrets (T-independent in the cumulative form) and validate this result through empirical evaluation.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948214
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 4:10 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 15:17 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 8:30 
 0
 0
 0
 0
 14:17 
 0
 0
 0
 0
 10:19 
 0
 0
 0
 0
 18:34 
 0
 0
 0
 0
 2:49 
 0
 0
 0
 0
 3:07 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 13:26 
 0
 0
 0
 0
 14:12 
 0
 0
 0
 0
 2:21 
 0
 0
 0
 0
 14:20 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 14:40 
 0
 0
 0
 0
 10:52 
 0
 0
 0
 0
 13:11 
 0
 0
 0
 0
 3:14 
 0
 0
 0
 0
 15:03 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 15:07 
 0
 0
 0
 0
 15:40 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 16:28 
 0
 0
 0
 0
 17:13 
 0
 0
 0
 0
 5:34 
 0
 0
 0
 0
 13:52 
 0
 0
 0
 0
 14:49 
 0
 0
 0
 0
 11:18 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 9:50 
 0
 0
 0
 0
 24:59